© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176560
    Prev
    Next
    INDEX
    Explanations

    import followed by statistical libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_24_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stof
    0.40
    textbf
    0.39
     Stress
    0.36
    ligen
    0.35
    Stress
    0.35
    addData
    0.34
    _,
    0.34
     పేర్కొ
    0.34
     Year
    0.34
     يس
    0.34
    POSITIVE LOGITS
    ኝ
    0.46
     Lancashire
    0.43
     médicament
    0.42
    atorias
    0.41
     midfield
    0.41
     रौ
    0.40
     Magdeburg
    0.40
    ॉन्स
    0.40
    勮
    0.40
    istically
    0.39
    Activations Density 0.002%

    No Known Activations